An investigation on local minima of a Hopfield network for optimization circuits
- 1 January 1988
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 45-51 vol.1
- https://doi.org/10.1109/icnn.1988.23827
Abstract
The Hopfield architecture can be utilized in the VLSI implementation of several important optimization functions. A description is given of the properties of local minima in the energy function of Hopfield networks. A novel design technique to eliminate such local minima has been developed. The neural-based analog-to-digital converter is used as an example to demonstrate this design technique. Experimental results agree well with theoretical calculations on the output characteristics of the analog-to-digital converter.Keywords
This publication has 4 references indexed in Scilit:
- An associative memory based on an electronic neural network architectureIEEE Transactions on Electron Devices, 1988
- Analog MOS integrated circuits-certain new ideas, trends, and obstaclesIEEE Journal of Solid-State Circuits, 1987
- Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuitIEEE Transactions on Circuits and Systems, 1986
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984